Skip to content

Leveraging Inference-Time Compute for Diffusion Models via Global Scheduling of Denoising Trajectories

Sep 2026 · 0 citations · 57 references
Computer Science

TL;DR

The analysis from independent random search to a broader family of local search operators, and it is proved that when sensitivities vary across instances, no adaptive policy can avoid worst-case regret that grows linearly in the trajectory length.

Abstract

Diffusion models generate a sample by traversing a denoising trajectory, a sequence of stochastic noise-reduction steps that transforms pure noise into a draw from a target distribution. At deployment time, additional computation can improve sample quality without retraining: at each step, the sampler draws several candidate noise samples, scores the resulting predictions with a quality criterion called the verifier, and retains the best candidate at the cost of one network evaluation per candidate. This raises a resource allocation question: given a fixed budget of function evaluations, how should search effort be distributed across the steps of the denoising trajectory? We formulate this as a computational budget allocation problem. First, we show that, to leading order in the step size, the expected gain from evaluating $K$ candidates at a step factorizes into an endogenous, step-specific sensitivity parameter times a universal sample-size factor equal to the expected best of $K$ standard-normal draws. Second, for a fixed sensitivity profile, the optimal allocation solves a separable concave integer program with water-filling structure; at fixed total sensitivity, its advantage over uniform allocation increases with sensitivity dispersion in the majorization order. Third, we prove that when sensitivities vary across instances, no adaptive policy can avoid worst-case regret that grows linearly in the trajectory length, which motivates a design that anchors the allocation offline and adapts online only to recover instance-specific slack. We extend the analysis from independent random search to a broader family of local search operators, and instantiate it as an implementable algorithm. Experiments on three families of diffusion samplers show that the proposed allocation attains the quality of the uniform benchmark with 20 to 50 percent fewer function evaluations.

View source

Similar papers

#artificial intelligence Preprint Sep 2026

Accelerating Video Diffusion via Training-Free Trajectory Routing

TRACK: TRajectory-Aware Capacity routing via top-K selection is presented, a heterogeneous denoising strategy that switches between compatible large and small models at selected steps, reducing the average cost per denoising evaluation.

Mustafa Munir, Huy Vu, Shreyas Misra et al. · 0 citations
#data science Sep 2026

FluxLite: Inference-Time Proposal Control for Discrete Diffusion Models

FluxLite is introduced, a lightweight, training-free proposal-control framework for discrete diffusion, identifying a tilted-path coverage factor that governs robustness to score error, together with finite-particle convergence for a fixed controlled Feynman-Kac recursion.

Yinuo Ren, Haoxuan Chen, Grant M. Rotskoff et al. · 1 citation
#artificial intelligence Preprint Sep 2026

GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion Trajectories

GeometricSPRINT (Geometric Step Pruning for Inference in Trajectories), a training-free framework for constructing non-uniform sampling schedules from the geometry of denoising trajectories, consistently improves over uniform DDIM (Denoising Diffusion Implicit Models) schedules at matched NFE budgets.

Arpita Joshi · 0 citations
#machine learning Preprint Sep 2026

Parallel Tempering for Diffusion-Based Combinatorial Optimization

Discrete diffusion models have emerged as a powerful paradigm for solving combinatorial optimization (CO) problems on graphs by learning to sample high-quality solutions. A common inference-time approach is to generate multiple candidate solutions independently and return the best-performing sample, improving solution...

Arman Mielke, Uwe Bauknecht, Thilo Strauss et al. · 0 citations
#machine learning Preprint Sep 2026

Denoising Surface: Modeling and Predicting Inference Cost for Diffusion LLM Serving

As diffusion large language models (dLLMs) become more capable, they are moving from research settings to real-world \textit{serving}, where request management (such as scheduling and resource allocation) relies on accurate estimation of per-request inference cost. However, common cost proxies fall short for dLLMs: out...

Hao-Yu Zheng, Fang-Cheng Fu, Bin-Hang Yuan et al. · 0 citations
#machine learning Preprint Sep 2026

A Splitting Method for SDE Terminal-Law Estimation

In many settings involving stochastic differential equations, including in diffusion based generative AI, our aim is to accurately generate samples from a terminal distribution. Typically, this is done by generating i.i.d. samples of diffusion paths. Given a fixed simulation budget, a reasonable way to gain efficiency...

Rushil Gupta, S. Juneja · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.